© Neuronpedia 2026
    Privacy & TermsBlogGitHubSlackTwitterContact
    Neuronpedia logo - a computer chip with a rounded viewfinder border around it

    Neuronpedia

    Jacobian LensNEW
    Natural Language
    Autoencoders
    NEW    Assistant AxisNEWCircuit TracerUPDATESteerSAE EvalsExportsinterp-engineNEWAPI Community BlogPrivacy & TermsContact
    1. Home
    3. Gemma-3-27B
    5. 31-GEMMASCOPE-2-RES-262K
    7. 30345
    Prev
    Next
    INDEX
    Explanations

    exact, approximate, rough, hidden

    np_acts-logits-general · gemini-2.5-flash-lite

    al dente

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Top Features by Cosine Similarity
    Configuration
    google/gemma-scope-2-27b-pt/resid_post/layer_31_width_262k_l0_medium
    Prompts (Dashboard)
    392,802 prompts, 256 tokens each
    Dataset (Dashboard)
    monology/pile-uncopyrighted
    No Configuration Found
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
     பக்தர்கள்
    0.50
    <unused27>
    0.47
     विराम
    0.46
    헌
    0.46
     செய்யப்பட்டது
    0.45
    <unused41>
    0.44
     ሲ
    0.44
     Leistungen
    0.44
    <unused14>
    0.44
     alpin
    0.44
    POSITIVE LOGITS
    с
    0.48
    Center
    0.46
     MAJOR
    0.42
    р
    0.41
    BE
    0.41
    Maximum
    0.41
    (:,
    0.41
     discontinuities
    0.40
     осу
    0.40
     BE
    0.40
    Activations Density 0.000%

    No Known Activations